Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Building Effective "Agents"

anthropic.com

Post reply on HN
Print view View original

111–120 of 130 posts

Re: Building Effective "Agents"

#111

Post by th0ma5 »

simonw wrote: post #104
th0ma5 wrote: post #102

Earlier quoted context omitted.

Lots of lists of the myths of LLMs out there https://masterofcode.com/blog/llms-myths-vs-reality-what-you... Every single post glosses over some aspect of these myths or posits they can be controlled or mitigated in some way, with no examples of anyone else finding applicability of the solutions to real world problems in a supportable and reliable way. When pushed, a myth in the neighborhood of those in the list abov…

I've written extensively about myths and misconceptions about LLMs, much of which overlaps with the observations in that post. Here's my series about misconceptions: https://simonwillison.net/series/llm-misconceptions/ It doesn't seem to me that you're familiar with my work - you seem to be mixing me in with the vast ocean of uncritical LLM boosting content that's out there.

I'm thinking of the system you built to watch videos and parse JSON and the claims of that having a general suitability, which is simply dishonest imo. You seem to be confusing me with someone that hasn't been asking you repeatedly to address these kinds of concerns and the above series are a kind of potemkin set of things that don't intersect with your other work.

Re: Building Effective "Agents"

#112

Post by th0ma5 »

famouswaffles wrote: post #110
th0ma5 wrote: post #93

Earlier quoted context omitted.

This is the location of the arguments. When they work they're "magical" but when they don't work "well people or other things are just as bad" ... And this means that you just cannot reason with the mysticism people have surrounding these things because show stopper problems are minimized or it is implied that they can somehow be reduced. The whole rest of computing does not work this way. So, you can't get the magic…

It's one thing if you're up against the staunch reliability of traditional algorithmic systems but if you're not then it's just silly to hang on it. You are not getting 100% on email handling whatever method you wish to use. You compare LLMs or probabilistic systems to the best of your alternatives. There are niches where the lack of complete reliability would be a deal breaker. This isn't one of them and it would be…

I don't think people are aware of the line at all. You ask five different people which things are reliable in any of these systems and you'll get five different guesses. C'mon here.

Re: Building Effective "Agents"

#113

Post by tomrod »

furyofantares wrote: post #45
tomrod wrote: post #44

Earlier quoted context omitted.

Brains are split internally, with each having their own monologue. One happens to have command.

I don't think there's reason to believe both halves have a monologue, is there? Experience, yes, but doesn't only one half do language?

[0] https://www.youtube.com/watch?v=fJRx9wItvKo

[1] https://thersa.org/globalassets/pdfs/blogs/rsa-divided-brain...

[2] https://en.wikipedia.org/wiki/Lateralization_of_brain_functi...

You have two minds (at least). One happens to be dominant.

Re: Building Effective "Agents"

#114

Post by famouswaffles »

th0ma5 wrote: post #112
famouswaffles wrote: post #110

Earlier quoted context omitted.

It's one thing if you're up against the staunch reliability of traditional algorithmic systems but if you're not then it's just silly to hang on it. You are not getting 100% on email handling whatever method you wish to use. You compare LLMs or probabilistic systems to the best of your alternatives. There are niches where the lack of complete reliability would be a deal breaker. This isn't one of them and it would be…

I don't think people are aware of the line at all. You ask five different people which things are reliable in any of these systems and you'll get five different guesses. C'mon here.

That's not what i'm talking about though. The point is that for spam detection, LLMs are up against other probabilistic measures. No-one sane is detecting spam with if-then's. You simply do not have the luxury of rigid reliability.

Re: Building Effective "Agents"

#115

Post by minasmorath »

pvg wrote: post #71
Animats wrote: post #50

Earlier quoted context omitted.

Yes, they have actionable definitions, but they are defining something quite different than the normal definition of an "agent". An agent is a party who acts for another. Often this comes from an employer-employee relationship. This matters mostly when things go wrong. Who's responsible? The airline whose AI agent gave out wrong info about airline policies found, in court, that their "intelligent agent" was considere…

AI people have been using a much broader definition of 'agent' for ages, though. One from Russel and Norvig's 90s textbook: "Anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators" https://en.wikipedia.org/wiki/Intelligent_agent#As_a_definit...

That definition feels like it's playing on the verb, the idea of having "agency" in the world, and not on the noun, of being an "agent" for another party. The former is a philosophical category, while the latter has legal meaning and implication, and it feels somewhat disingenuous to continue to mix them up in this way.

Re: Building Effective "Agents"

#116

Post by AnimalMuppet »

minasmorath wrote: post #115
pvg wrote: post #71

Earlier quoted context omitted.

AI people have been using a much broader definition of 'agent' for ages, though. One from Russel and Norvig's 90s textbook: "Anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators" https://en.wikipedia.org/wiki/Intelligent_agent#As_a_definit...

That definition feels like it's playing on the verb, the idea of having "agency" in the world, and not on the noun, of being an "agent" for another party. The former is a philosophical category, while the latter has legal meaning and implication, and it feels somewhat disingenuous to continue to mix them up in this way.

Interesting. The best agents don't have agency, or at least don't use it.

You can think of this in video game terms: Players have agency. NPCs are "agencs", but don't have agency. But they're still not just objects in the game - they can move themselves and react to their environment.

Re: Building Effective "Agents"

#117

Post by pvg »

minasmorath wrote: post #115
pvg wrote: post #71

Earlier quoted context omitted.

AI people have been using a much broader definition of 'agent' for ages, though. One from Russel and Norvig's 90s textbook: "Anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators" https://en.wikipedia.org/wiki/Intelligent_agent#As_a_definit...

That definition feels like it's playing on the verb, the idea of having "agency" in the world, and not on the noun, of being an "agent" for another party. The former is a philosophical category, while the latter has legal meaning and implication, and it feels somewhat disingenuous to continue to mix them up in this way.

In what way is it 'disingenuous'? You think Norvig is trying to deceive us about something? I'm not saying you have to agree with or like this definition but even if you think it's straight up wrong, 'disingenuous' feels utterly out of nowhere.

Re: Building Effective "Agents"

#118

Post by rcxdude »

Nekit1234007 wrote: post #87
simonw wrote: post #73

Earlier quoted context omitted.

That logic doesn't work for me, because many words have multiple meanings. "Agency" can also be a noun that means an organization that you hire - like a design agency. Or it can mean the CIA. I'm not saying it's not a valid definition of the term, I'm pushing back on the idea that it's THE single correct definition of the term.

May I push back on the idea that a single word may mean (completely) different things?

You're pushing up against the english language, then. 'let' has 46 entries in the dictionary (more if you cinsider obsolete usages).

Re: Building Effective "Agents"

#119

Post by minasmorath »

pvg wrote: post #117
minasmorath wrote: post #115

Earlier quoted context omitted.

That definition feels like it's playing on the verb, the idea of having "agency" in the world, and not on the noun, of being an "agent" for another party. The former is a philosophical category, while the latter has legal meaning and implication, and it feels somewhat disingenuous to continue to mix them up in this way.

In what way is it 'disingenuous'? You think Norvig is trying to deceive us about something? I'm not saying you have to agree with or like this definition but even if you think it's straight up wrong, 'disingenuous' feels utterly out of nowhere.

It's disingenuous in that it takes a word with a common understanding ("agent") and then conveniently redefines or re-etomologizes the word in an uncommon way that leads people to implicitly believe something about the product that isn't true.

Another great example of this trick is "essential" oils. We all know what the word "essential" means, but the companies selling the stuff use the word in the most uncommon way, to indicate the "essence" of something is in the oil, and then let the human brain fill in the gap and thus believe something that isn't true. It's techinically legal, but we have to agree that's not moral or ethical, right?

Maybe I'm wildly off base here, I have admittedly been wrong about a lot in my life up to this point. I just think the backlash that crops up when people realize what's going on (for example, the airline realizing that their chat bot does not in fact operate under the same rules as a human "agent," and that it's still a technology product) should lead companies to change their messaging and marketing, and the fact that they're just doubling down on the same misleading messaging over and over makes the whole charade feel disingenuous to me.

Re: Building Effective "Agents"

#120

Post by minasmorath »

AnimalMuppet wrote: post #116
minasmorath wrote: post #115

Earlier quoted context omitted.

That definition feels like it's playing on the verb, the idea of having "agency" in the world, and not on the noun, of being an "agent" for another party. The former is a philosophical category, while the latter has legal meaning and implication, and it feels somewhat disingenuous to continue to mix them up in this way.

Interesting. The best agents don't have agency, or at least don't use it. You can think of this in video game terms: Players have agency. NPCs are "agencs", but don't have agency. But they're still not just objects in the game - they can move themselves and react to their environment.

That's actually a great example of what I'm saying, because I don't think the NPCs are agents at all in the traditional sense of "One that acts or has the power or authority to act on behalf of another." Where would the NPC derive its power and authority from? There is a human somewhere in the chain giving it 100% of its parameters, and that human is ultimately 100% responsible for the configuration of the NPC, which is why we don't blame the NPC in the game for behaving in a buggy way, we blame the devs. To say the NPC has agency puts some level of metaphysical responsibility about decision making and culpability on the thing that it doesn't have.

An AI "agent" is the same way, it is not culpable for its actions, the humans who set it up are, but we're leading people to believe that if the AI goes off script then the AI is somehow responsible for its own actions, which is simply not true. These are not autonomous beings, they're technology products.

Post reply on HN